update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- summarization
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: t5-small-booksum-finetuned-booksum-test
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# t5-small-booksum-finetuned-booksum-test
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [cnicu/t5-small-booksum](https://huggingface.co/cnicu/t5-small-booksum) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 3.2739
|
| 21 |
+
- Rouge1: 22.7829
|
| 22 |
+
- Rouge2: 4.8349
|
| 23 |
+
- Rougel: 18.2465
|
| 24 |
+
- Rougelsum: 19.2417
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 5.6e-05
|
| 44 |
+
- train_batch_size: 1
|
| 45 |
+
- eval_batch_size: 1
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 8
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|
|
| 55 |
+
| 3.5123 | 1.0 | 8750 | 3.2816 | 21.7712 | 4.3046 | 17.4053 | 18.4707 |
|
| 56 |
+
| 3.2347 | 2.0 | 17500 | 3.2915 | 22.2938 | 4.7828 | 17.8567 | 18.9135 |
|
| 57 |
+
| 3.0892 | 3.0 | 26250 | 3.2568 | 22.4966 | 4.825 | 18.0344 | 19.1306 |
|
| 58 |
+
| 2.9837 | 4.0 | 35000 | 3.2952 | 22.6913 | 5.0322 | 18.176 | 19.2751 |
|
| 59 |
+
| 2.9028 | 5.0 | 43750 | 3.2626 | 22.3548 | 4.7521 | 17.8681 | 18.7815 |
|
| 60 |
+
| 2.8441 | 6.0 | 52500 | 3.2691 | 22.6279 | 4.932 | 18.1051 | 19.0763 |
|
| 61 |
+
| 2.8006 | 7.0 | 61250 | 3.2753 | 22.8911 | 4.8954 | 18.1204 | 19.1464 |
|
| 62 |
+
| 2.7742 | 8.0 | 70000 | 3.2739 | 22.7829 | 4.8349 | 18.2465 | 19.2417 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.19.1
|
| 68 |
+
- Pytorch 1.7.0
|
| 69 |
+
- Datasets 2.2.1
|
| 70 |
+
- Tokenizers 0.12.1
|